Skip to content

Benchmark

MMAU Music

Scores are percentages.

Models measured
6
Scores recorded
11
Sources
2
IQ weight
0.73

Score distribution

64.2%
Mean
64.8%
Median
4.1%
Std dev
59.3%
10th percentile
69.2%
90th percentile
54.9%
Min
54.9%69.4%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.73 for chat models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Gemini 2.5 FlashTest· MMAU (audio) data69.4%
2Qwen2.5-Omni 7B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.2%
3Gemini 2.5 ProTest-mini· MMAU (audio) data68.3%
4Gemini 2.5 FlashTest-mini· MMAU (audio) data65.6%
5Gemini 2.0 FlashTest-mini· MMAU (audio) data65.3%
6Gemini 2.5 ProTest· MMAU (audio) data64.8%
7Phi 4 Multimodal InstructTest-mini· MMAU (audio) data64.4%
8Gemini 2.5 Flash-LiteTest-mini· MMAU (audio) data63.5%
9Phi 4 Multimodal InstructTest· MMAU (audio) data62%
10Gemini 2.0 FlashTest· MMAU (audio) data59.3%
11Gemini 2.5 Flash-LiteTest· MMAU (audio) data54.9%

Data credits: Data by LLM Stats